Type Alias: LLamaChatLoadAndCompleteUserMessageOptions<Functions>
type LLamaChatLoadAndCompleteUserMessageOptions<Functions> = {
initialUserPrompt?: string;
stopOnAbortSignal?: boolean;
onTextChunk?: LLamaChatGenerateResponseOptions<Functions>["onTextChunk"];
onToken?: LLamaChatGenerateResponseOptions<Functions>["onToken"];
signal?: LLamaChatGenerateResponseOptions<Functions>["signal"];
maxTokens?: LLamaChatGenerateResponseOptions<Functions>["maxTokens"];
temperature?: LLamaChatGenerateResponseOptions<Functions>["temperature"];
minP?: LLamaChatGenerateResponseOptions<Functions>["minP"];
topK?: LLamaChatGenerateResponseOptions<Functions>["topK"];
topP?: LLamaChatGenerateResponseOptions<Functions>["topP"];
seed?: LLamaChatGenerateResponseOptions<Functions>["seed"];
trimWhitespaceSuffix?: LLamaChatGenerateResponseOptions<Functions>["trimWhitespaceSuffix"];
repeatPenalty?: LLamaChatGenerateResponseOptions<Functions>["repeatPenalty"];
tokenBias?: LLamaChatGenerateResponseOptions<Functions>["tokenBias"];
evaluationPriority?: LLamaChatGenerateResponseOptions<Functions>["evaluationPriority"];
contextShift?: LLamaChatGenerateResponseOptions<Functions>["contextShift"];
customStopTriggers?: LLamaChatGenerateResponseOptions<Functions>["customStopTriggers"];
lastEvaluationContextWindow?: LLamaChatGenerateResponseOptions<Functions>["lastEvaluationContextWindow"];
grammar?: LlamaGrammar;
functions?: Functions | ChatModelFunctions;
documentFunctionParams?: boolean;
};
Defined in: evaluator/LlamaChat/LlamaChat.ts:352
Type Parameters
Type Parameter | Default type |
---|---|
Functions extends ChatModelFunctions | undefined | undefined |
Properties
initialUserPrompt?
optional initialUserPrompt: string;
Defined in: evaluator/LlamaChat/LlamaChat.ts:356
Complete the given user prompt without adding it or the completion to the returned context window.
stopOnAbortSignal?
optional stopOnAbortSignal: boolean;
Defined in: evaluator/LlamaChat/LlamaChat.ts:364
When a completion already started being generated and then the signal is aborted, the generation will stop and the completion will be returned as is instead of throwing an error.
Defaults to false
.
onTextChunk?
optional onTextChunk: LLamaChatGenerateResponseOptions<Functions>["onTextChunk"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:371
Called as the model generates a completion with the generated text chunk.
Useful for streaming the generated completion as it's being generated.
onToken?
optional onToken: LLamaChatGenerateResponseOptions<Functions>["onToken"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:378
Called as the model generates a completion with the generated tokens.
Preferably, you'd want to use onTextChunk
instead of this.
signal?
optional signal: LLamaChatGenerateResponseOptions<Functions>["signal"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:380
maxTokens?
optional maxTokens: LLamaChatGenerateResponseOptions<Functions>["maxTokens"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:381
temperature?
optional temperature: LLamaChatGenerateResponseOptions<Functions>["temperature"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:382
minP?
optional minP: LLamaChatGenerateResponseOptions<Functions>["minP"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:383
topK?
optional topK: LLamaChatGenerateResponseOptions<Functions>["topK"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:384
topP?
optional topP: LLamaChatGenerateResponseOptions<Functions>["topP"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:385
seed?
optional seed: LLamaChatGenerateResponseOptions<Functions>["seed"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:386
trimWhitespaceSuffix?
optional trimWhitespaceSuffix: LLamaChatGenerateResponseOptions<Functions>["trimWhitespaceSuffix"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:387
repeatPenalty?
optional repeatPenalty: LLamaChatGenerateResponseOptions<Functions>["repeatPenalty"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:388
tokenBias?
optional tokenBias: LLamaChatGenerateResponseOptions<Functions>["tokenBias"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:389
evaluationPriority?
optional evaluationPriority: LLamaChatGenerateResponseOptions<Functions>["evaluationPriority"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:390
contextShift?
optional contextShift: LLamaChatGenerateResponseOptions<Functions>["contextShift"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:391
customStopTriggers?
optional customStopTriggers: LLamaChatGenerateResponseOptions<Functions>["customStopTriggers"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:392
lastEvaluationContextWindow?
optional lastEvaluationContextWindow: LLamaChatGenerateResponseOptions<Functions>["lastEvaluationContextWindow"];
Defined in: evaluator/LlamaChat/LlamaChat.ts:393
grammar?
optional grammar: LlamaGrammar;
Defined in: evaluator/LlamaChat/LlamaChat.ts:395
functions?
optional functions: Functions | ChatModelFunctions;
Defined in: evaluator/LlamaChat/LlamaChat.ts:404
Functions are not used by the model here, but are used for keeping the instructions given to the model about the functions in the current context state, to avoid context shifts.
It's best to provide the same functions that were used for the previous prompt here.
documentFunctionParams?
optional documentFunctionParams: boolean;
Defined in: evaluator/LlamaChat/LlamaChat.ts:413
Functions are not used by the model here, but are used for keeping the instructions given to the model about the functions in the current context state, to avoid context shifts.
It's best to provide the same value that was used for the previous prompt here.